FunASR
by modelscope
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
1. Made by
Listed in the official MCP registry as io.github.modelscope/funasr-mcp. We have not checked who runs it.
github.com/modelscope/FunASR3. Runs
github.com/modelscope/FunASRFrom the official MCP registry entry. Tap a verdict to see its source.How we checkedReport an error
What FunASR does
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
FunASR popularity
Tools it gives your agent
We have not listed its tools yet. The registry entry does not include them; they appear once we read the server's code.
Is it alive
0.1.2 in the registry, updated Jul 26, 2026
Alternatives
FunASR This page
Draw and visually collaborate with your agents on tldraw's canvas.
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Search your local screen recordings, audio transcripts, and computer activity from screenpipe.
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Get started
Connect it
docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2No step-by-step start for FunASR yet: these commands come from its registry entry; we have not checked its docs.